In this session, you learnt how information flows from the input layer to the output layer in Artificial Neural Networks (feedforward). You studied feedforward for a regression problem based on the housing price prediction problem statement. You also learnt how to specify the dimensions and representations of the weight matrices, biases, inputs and outputs, etc., of the various layers.
You developed an understanding of how feedforward can be done in a vectorised form.
In order to train a neural network, you need to optimise the weights and biases of the network, and you need to use optimisation techniques such as gradient descent to do this.
In the next module, you will learn about the process of training a neural network using backpropagation.
Report an error